We present the next generation of MobileNets based on a combination of complementary
search techniques as well as a novel architecture design. MobileNetV3 is tuned to mobile�…

Despite the blooming success of architecture search for vision tasks in resource-constrained
environments, the design of on-device object detection architectures have mostly been�…

Depthwise convolution is becoming increasingly popular in modern efficient ConvNets, but
its kernel size is often overlooked. In this paper, we systematically study the impact of�…

Convolutional networks have enjoyed much success in many computer vision applications.
The convolution operation however has a significant weakness in that it only operates on a�…

Recently, channel attention mechanism has demonstrated to offer great potential in
improving the performance of deep convolutional neural networks (CNNs). However, most�…

Deep neural networks have achieved remarkable success in computer vision tasks. Existing
neural networks mainly operate in the spatial domain with fixed input sizes. For practical�…

Designing convolutional neural networks (CNN) for mobile devices is challenging because
mobile models need to be small and fast, yet still accurate. Although significant efforts have�…

The inverted residual block is dominating architecture design for mobile networks recently. It
changes the classic residual bottleneck by introducing two design rules: learning inverted�…

Neural architecture search (NAS) has shown great potential in automating the manual
process of designing a good CNN architecture for image classification. In this paper, we�…

Neural architecture search (NAS) has achieved unprecedented performance in various
computer vision tasks. However, most existing NAS methods are defected in search�…